mlsanityData to 14 Oct 2026

LLMs achieve adult human performance on higher-order theory of mind tasks

arXiv 2405.18870 ↗First posted 29 May 2024cs.AI cs.CL cs.HCcited by 61

Not on the map. Why?

Abstract (arXiv)

This paper examines the extent to which large language models (LLMs) have developed higher-order theory of mind (ToM); the human ability to reason about multiple mental and emotional states in a recursive manner (e.g. I think that you believe that she knows). This paper builds on prior work by introducing a handwritten test suite -- Multi-Order Theory of Mind Q&A -- and using it to compare the performance of five LLMs to a newly gathered adult human benchmark. We find that GPT-4 and Flan-PaLM reach adult-level and near adult-level performance on ToM tasks overall, and that GPT-4 exceeds adult performance on 6th order inferences. Our results suggest that there is an interplay between model size and finetuning for the realisation of ToM abilities, and that the best-performing LLMs have developed a generalised capacity for ToM. Given the role that higher-order ToM plays in a wide range of cooperative and competitive human behaviours, these findings have significant implications for user-facing LLM applications.

Key facts. Cited by 61 papers in the map (data through 14 Oct 2026). Builds on 29 of its 90 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

29 of 90 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  8. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  9. 2023A Survey of Large Language Modelscited by 2,576
  10. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  11. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  12. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
17 more
  1. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  2. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  3. 2020Scaling Laws for Autoregressive Generative Modelingcited by 522
  4. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 292
  5. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
  6. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  7. 2023Understanding Social Reasoning in Language Models with Language Modelscited by 172
  8. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 163
  9. 2022The Debate Over Understanding in AI's Large Language Modelscited by 142
  10. 2024The Ethics of Advanced AI Assistantscited by 107
  11. 2022Meaning without reference in large language modelscited by 76
  12. 2023HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Modelscited by 63
  13. 2023Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Testscited by 48
  14. 2024A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AIcited by 34
  15. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  16. 2024LLM Theory of Mind and Alignment: Opportunities and Riskscited by 18
  17. 2023Predictable Artificial Intelligencecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 25; 2026: 20.

61 papers.

Sort:

By area:

  1. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?cited by 286
  2. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 166
  3. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  4. 2025Language Models use Lookbacks to Track Beliefscited by 39
  5. 2024The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Unitscited by 34
  6. 2024Position: Theory of Mind Benchmarks are Broken for Large Language Modelscited by 31
  7. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  8. 2025Theory of Mind in Large Language Models: Assessment and Enhancementcited by 25
  9. 2025Re-evaluating Theory of Mind evaluation in large language modelscited by 23
  10. 2024Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Modelscited by 22
  11. 2025Population-Aligned Persona Generation for LLM-based Social Simulationcited by 21
  12. 2024II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Modelscited by 16
38 more
  1. 2024Can LLMs make trade-offs involving stipulated pain and pleasure states?cited by 16
  2. 2024Perceptions of Linguistic Uncertainty by Language Models and Humanscited by 15
  3. 2024Can MLLMs Understand the Deep Implication Behind Chinese Images?cited by 14
  4. 2024From Imitation to Introspection: Probing Self-Consciousness in Language Modelscited by 14
  5. 2025ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mindcited by 12
  6. 2024In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Modelscited by 8
  7. 2024Codenames as a Benchmark for Large Language Modelscited by 8
  8. 2025A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Riskscited by 8
  9. 2025PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehuntscited by 8
  10. 2025LVLMs are Bad at Overhearing Human Referential Communicationcited by 8
  11. 2024Organizing Unstructured Image Collections using Natural Languagecited by 7
  12. 2025Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewardscited by 6
  13. 2025Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agentscited by 5
  14. 2025First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimationcited by 5
  15. 2026Social-R1: Towards Human-like Social Reasoning in LLMscited by 5
  16. 2025Teaching AI to Handle Exceptions: Supervised Fine-Tuning with Human-Aligned Judgmentcited by 4
  17. 2025Towards properly implementing Theory of Mind in AI systems: An account of four misconceptionscited by 3
  18. 2025DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logiccited by 3
  19. 2025AI-enhanced semantic feature norms for 786 conceptscited by 2
  20. 2026Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mindcited by 2
  21. 2026Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectivescited by 2
  22. 2024Heads Up eXperience (HUX): Always-On AI Companion for Human Computer Environment Interactioncited by 1
  23. 2025Event Segmentation Applications in Large Language Model Enabled Automated Recall Assessmentscited by 1
  24. 2025BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mindcited by 1
  25. 2025Conversational Alignment with Artificial Intelligence in Contextcited by 1
  26. 2025Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Modelscited by 1
  27. 2025Modeling the Mental World for Embodied AI: A Comprehensive Reviewcited by 1
  28. 2026Large Language Models Persuade Without Planning Theory of Mindcited by 1
  29. 2026Do LLMs have core beliefs?cited by 1
  30. 2026AI and Consciousness: Shifting Focus Towards Tractable Questionscited by 1
  31. 2026Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Actioncited by 1
  32. 2026Inducing language models to assert their own consciousness restores human beliefs and valuescited by 1
  33. 2026Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisionscited by 1
  34. 2024Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Modelscited by 0
  35. 2025Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Modelscited by 0
  36. 2025Theory of Mind in Action: The Instruction Inference Task in Dynamic Human-Agent Collaborationcited by 0
  37. 2025Polymorphic Combinatorial Frameworks (PCF): Guiding the Design of Mathematically-Grounded, Adaptive AI Agentscited by 0
  38. 2025SocialNLI: A Dialogue-Centric Social Inference Datasetcited by 0

50 most cited of 61 All 61 (JSON)